CN115665323A - Outbound fault analysis method and device, computer equipment and storage medium - Google Patents
Outbound fault analysis method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115665323A CN115665323A CN202211182229.2A CN202211182229A CN115665323A CN 115665323 A CN115665323 A CN 115665323A CN 202211182229 A CN202211182229 A CN 202211182229A CN 115665323 A CN115665323 A CN 115665323A
- Authority
- CN
- China
- Prior art keywords
- outbound
- time period
- failure
- fault type
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 37
- 238000003062 neural network model Methods 0.000 claims abstract description 60
- 238000000034 method Methods 0.000 claims abstract description 46
- 238000004590 computer program Methods 0.000 claims description 36
- 230000015654 memory Effects 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 12
- 238000012544 monitoring process Methods 0.000 description 11
- 238000013528 artificial neural network Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000002441 reversible effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000002759 z-score normalization Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to an outbound fault analysis method, an outbound fault analysis device, computer equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: inputting a time period to be predicted into a preset neural network model, and predicting the outbound failure rate in the time period and the outbound failure times corresponding to multiple failure types caused by the self failure of an outbound system in the time period; under the condition that the outbound failure rate is greater than a preset first threshold value, obtaining a weight weighting number corresponding to each fault type according to each outbound failure frequency and a preset weight value corresponding to each fault type; and determining the target fault type of the outbound failure in the time period according to the number of times of the outbound failure and the weighted number of the weights. By adopting the method, the fault type of the outbound failure can be accurately positioned.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a method and an apparatus for analyzing an outbound fault, a computer device, and a storage medium.
Background
As society develops, the outbound system becomes more and more common in life. For example, a bank may simulate a manual call through an outbound system, placing calls to a large number of users simultaneously. However, the outbound system may have a large amount of concurrency, which may cause a task to be blocked, or may have a failure in the outbound system itself, which may cause a call to be unavailable. Therefore, it is important to analyze the reason why the outgoing call system failed to make a call in the normal operation of the outgoing call system.
In the conventional technology, the availability of each module constituting the outbound system is mainly monitored, for example, an error will be reported when some components of the outbound system cannot be used, an error will also be reported when some errors occur in the outbound system, and an alarm message will also be generated when some log outputs an error keyword.
However, the conventional technique has a problem that the type of the failure cannot be accurately located.
Disclosure of Invention
In view of the foregoing, it is necessary to provide an outbound fault analysis method, apparatus, computer device and storage medium capable of accurately locating the fault type.
In a first aspect, the present application provides a method for analyzing an outbound fault. The method comprises the following steps:
inputting a time period to be predicted into a preset neural network model, and predicting the outbound failure rate in the time period and the outbound failure times corresponding to multiple fault types caused by the faults of an outbound system in the time period;
under the condition that the outbound failure rate is greater than a preset first threshold, obtaining a weight weighting number corresponding to each fault type according to each outbound failure frequency and a preset weight value corresponding to each fault type;
and determining the target fault type of the outbound failure in the time period according to the number of the outbound failures and the weighted number of the weights.
In one embodiment, the determining, according to the number of outbound failures and the weighted weight of each outbound failure, the target failure type of the outbound failure occurring in the time period includes:
determining the candidate fault types of the outbound failures occurring in the time period according to the number of the outbound failures;
determining the weight weighting number corresponding to the candidate fault type according to the weight weighting numbers;
and determining the target fault type from the candidate fault types according to the weight weighting number corresponding to the candidate fault types.
In one embodiment, the determining the target fault type from the candidate fault types according to the weighted weight corresponding to the candidate fault type includes:
and determining the candidate fault type with the weight number larger than a preset second threshold value as the target fault type.
In one embodiment, the method further comprises:
and outputting alarm prompt information under the condition that the outbound failure rate is greater than the preset first threshold value.
In one embodiment, the training process of the neural network model includes:
acquiring the total outbound failure times in a sample time period and standard outbound failure times corresponding to multiple fault types caused by the faults of an outbound system;
determining a standard outbound failure rate corresponding to the sample time period according to each standard outbound frequency and the total outbound failure frequency;
inputting the sample time period into an initial neural network model, and predicting the sample outbound failure rate in the sample time period and the sample outbound failure times corresponding to multiple fault types occurring in the sample time period;
and training the initial neural network model according to the standard outbound failure rate, the standard outbound failure times, the sample outbound failure rate and the sample outbound failure times to obtain the neural network model.
In a second aspect, the application further provides an outbound fault analysis device. The device comprises:
the prediction module is used for inputting a time period to be predicted into a preset neural network model, and predicting the outbound failure rate in the time period and the outbound failure times corresponding to multiple fault types caused by the faults of the outbound system in the time period;
the calculation module is used for obtaining a weight weighting number corresponding to each fault type according to each outbound failure frequency and a preset weight value corresponding to each fault type under the condition that the outbound failure rate is greater than a preset first threshold value;
and the determining module is used for determining the target fault type of the outbound failure occurring in the time period according to the number of the outbound failures and the weighted number of the weights.
In a third aspect, the application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the following steps when executing the computer program:
inputting a time period to be predicted into a preset neural network model, and predicting the outbound failure rate in the time period and the outbound failure times corresponding to multiple failure types caused by the self failure of an outbound system in the time period;
under the condition that the outbound failure rate is greater than a preset first threshold, obtaining a weight weighting number corresponding to each fault type according to each outbound failure frequency and a preset weight value corresponding to each fault type;
and determining the target fault type of the outbound failure in the time period according to the number of the outbound failures and the weighted number of the weights.
In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
inputting a time period to be predicted into a preset neural network model, and predicting the outbound failure rate in the time period and the outbound failure times corresponding to multiple fault types caused by the faults of an outbound system in the time period;
under the condition that the outbound failure rate is greater than a preset first threshold, obtaining a weight weighting number corresponding to each fault type according to each outbound failure frequency and a preset weight value corresponding to each fault type;
and determining the target fault type of the outbound failure occurring in the time period according to the number of the outbound failures and the weight of the weights.
In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:
inputting a time period to be predicted into a preset neural network model, and predicting the outbound failure rate in the time period and the outbound failure times corresponding to multiple fault types caused by the faults of an outbound system in the time period;
under the condition that the outbound failure rate is greater than a preset first threshold, obtaining a weight weighting number corresponding to each fault type according to each outbound failure frequency and a preset weight value corresponding to each fault type;
and determining the target fault type of the outbound failure in the time period according to the number of the outbound failures and the weighted number of the weights.
According to the method, the device, the computer equipment and the storage medium for analyzing the outbound fault, the time period to be predicted is input into the preset neural network model, the outbound failure rate in the time period and the outbound failure times corresponding to multiple fault types caused by the faults of the outbound system in the time period can be accurately predicted, so that under the condition that the outbound failure rate is larger than the preset first threshold value, the weight weighted number corresponding to each fault type is obtained according to the outbound failure times corresponding to each fault type and the preset weight value corresponding to each fault type, further, the target fault type of the outbound failure occurring in the time period can be determined according to the outbound failure times corresponding to each fault type and the weight weighted number corresponding to each fault type, and compared with the method for monitoring the availability of each module forming the outbound system in the prior art, the process can judge whether the outbound failure is caused by the concurrency overrun of the outbound system, and can accurately position the target fault type of the outbound failure caused by the faults of the outbound system in the time period to be predicted.
Drawings
FIG. 1 is a diagram of an application environment of a method for outbound fault analysis in one embodiment;
FIG. 2 is a schematic flow chart diagram illustrating a method for outbound fault analysis in one embodiment;
FIG. 3 is a schematic flow chart diagram illustrating a method for outbound fault analysis in accordance with another embodiment;
FIG. 4 is a schematic flow chart diagram illustrating a method for outbound fault analysis in accordance with another embodiment;
FIG. 5 is a schematic flow chart diagram illustrating a method for outbound fault analysis in accordance with another embodiment;
FIG. 6 is a block diagram of an outbound fault analysis device in one embodiment;
fig. 7 is a block diagram showing the structure of an outbound fault analysis apparatus in another embodiment;
fig. 8 is a block diagram showing the structure of an outbound fault analysis apparatus in another embodiment;
fig. 9 is a block diagram showing the structure of an outbound fault analysis apparatus according to another embodiment;
fig. 10 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It should be noted that the outbound fault analysis method, the outbound fault analysis device, the computer device and the storage medium of the present application may be applied in the technical field of artificial intelligence, and may also be applied in other technical fields except the technical field of artificial intelligence.
The outbound fault analysis method provided by the embodiment of the application can be applied to the application environment shown in fig. 1. Wherein, the computer device 104 may be integrated with an outbound system, and the computer device 104 may make calls to a plurality of terminals 102 simultaneously by using the outbound system. The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, and the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart car-mounted devices, and the like. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, and the like. The computer device 104 may be implemented as a stand-alone computer device or as a cluster of computer devices.
In the conventional technology, monitoring of the outbound system generally monitors the availability of each module constituting the outbound system, and if some components cannot be used, error information is generated; monitoring events when some errors occur in the outbound system, and generating alarm information when some logs output wrong keywords are detected; meanwhile, some important transaction monitoring can be provided, such as the generation condition of the intelligent outgoing call recording. The normal operation of the intelligent outbound system is ensured through the monitoring of the three different dimensions. However, conventional monitoring of outbound systems does not accurately locate the type of fault that has occurred with the outbound fault.
In one embodiment, as shown in fig. 2, an outbound fault analysis method is provided, which is described by taking the method as an example applied to the computer device in fig. 1, and includes the following steps:
s201, inputting a time period to be predicted into a preset neural network model, and predicting the outbound failure rate in the time period and the outbound failure times corresponding to multiple failure types caused by the faults of an outbound system in the time period.
The neural network model can be a long-term and short-term neural network LSTM and the like, and it can be understood that the LSTM has a long-term memory function, can memorize information for a long term, memorizes numerical values of indefinite time lengths and reduces the learning difficulty of the neural network. Optionally, in this embodiment, the first layer of the neural network model is an LSTM layer, and the second layer is a fully connected layer.
It can be understood that the external system may simultaneously make an outbound call to a plurality of terminals, and therefore, a call issued by the outbound system may fail to be outbound due to too large concurrency of the outbound system, or may fail to be outbound due to a fault of the outbound system itself, and generally, if the outbound system fails to be outbound due to too large concurrency of the outbound system, the call task may be issued again after a certain time. Illustratively, the outbound failure caused by the self-failure of the outbound system in this embodiment may be any one of an outbound failure caused by a call routing failure of the outbound system, an outbound failure caused by an unavailable server of the outbound system, and an outbound failure caused by an active release of the outbound system exceeding a service control ring timeout.
The outbound failure rate in the time period to be predicted in this embodiment is a ratio of the number of outbound failure times corresponding to multiple fault types caused by the faults of the outbound system in the time period to be predicted to the total number of calls issued by the outbound system.
Exemplarily, in the present embodiment, the time period to be predicted may be 8. Further, as an example, the number of calls issued by a 10:30 and 11: 00.
and S202, under the condition that the outbound failure rate is greater than a preset first threshold value, obtaining a weight weighting number corresponding to each fault type according to each outbound failure frequency and a preset weight value corresponding to each fault type.
The fault type in this embodiment may be determined according to a fault type corresponding to an outbound failure caused by a fault of the outbound system in a historical time period. The weight value corresponding to each fault type can be used for representing the importance degree of each fault type.
Optionally, the weight value corresponding to each fault type may be stored in the weight log in advance, and when the preset weight value corresponding to each fault type needs to be calculated, the preset weight value corresponding to each fault type may be directly obtained from the weight log. It can be understood that, when updating a plurality of fault types caused by the fault of the outbound system, the updated fault types can be synchronized into the weight log, even if the updated fault types and the weight values corresponding to the updated fault types are stored in the weight log. For example, the weight value corresponding to each fault type may be as shown in table 1.
TABLE 1
Specifically, the preset first threshold may be autonomously determined according to an empirical value, in this embodiment, if the outbound failure rate exceeds the preset first threshold, it indicates that the failure rate caused by the self failure of the outbound system is too high, which may affect the normal operation of the outbound system, so that the type of the outbound failure occurring in the time period needs to be determined so as to be solved in time. Optionally, in this embodiment, the outbound failure times corresponding to each fault type may be multiplied by the weight value corresponding to each fault type, so as to obtain the weight weighted value corresponding to each fault type. For example, if the number of outbound failure times corresponding to a certain fault type is 5 and the weight value corresponding to the fault type is 0.7, the weight weighting value corresponding to the fault type is 3.5.
And S203, determining the target fault type of the outbound failure occurring in the time period according to the outbound failure times and the weighted weight of each weight.
Optionally, in this embodiment, the target fault type of the outbound failure occurring in the time period may be determined according to the weight value corresponding to the fault type with the largest number of outbound failure times and the largest number of outbound failure times, for example, if the weight value corresponding to the fault type with the largest number of outbound failure times is the largest, the fault type may be determined as the target fault type. Further, the determined target fault type of the outbound failure occurring in the time period may be stored in a log, so that the user may conveniently confirm the fault type of the outbound failure occurring in the time period. For example, in this embodiment, the determined target fault type may be one fault type, or may be multiple fault types.
In the outbound fault analysis method, by inputting the time period to be predicted into a preset neural network model, the outbound failure rate in the time period and the outbound failure times corresponding to multiple fault types caused by the faults of the outbound system in the time period can be accurately predicted, so that under the condition that the outbound failure rate is greater than a preset first threshold value, according to the outbound failure times corresponding to the fault types and preset weighted values corresponding to the fault types, weight weighted numbers corresponding to the fault types are obtained, further, according to the outbound failure times corresponding to the fault types and the weight weighted numbers corresponding to the fault types, the target fault type of the outbound failure occurring in the time period is determined.
In the scenario that the target fault type of the outbound failure occurring in the time period to be predicted is determined according to the number of outbound failure times corresponding to each fault type and the weight weighting number corresponding to each fault type, candidate fault types can be determined first, and then the target fault type is determined from the candidate fault types. In an embodiment, as shown in fig. 3, the step S203 includes:
s301, determining candidate fault types of the outbound failure occurring in the time period according to the number of the outbound failure.
Optionally, in this embodiment, the outbound failure times corresponding to multiple failure types caused by the failure of the outbound system in the time period may be sorted in reverse order, and the first failure types sorted in reverse order are taken as candidate failure type types of the outbound failure occurring in the time period. For example, the top 5 failure types in reverse order of the number of failed calls may be determined as candidate failure types. Further, the determined candidate fault types may be stored in the log.
And S302, determining the weight weighting number corresponding to the candidate fault type according to the weight weighting numbers.
Optionally, in this embodiment, the weight weighting number corresponding to the candidate fault type may be searched from the weight weighting numbers corresponding to the fault types. For example, each fault type may include an a type, a B type, a C type, and a D type, the weight weighting corresponding to each fault type includes a weight weighting of the a type, a weight weighting of the B type, a weight weighting of the C type, and a weight weighting of the D type, and the candidate fault type may be the a type and the C type, and then the weight weighting of the candidate fault type may be determined from the weight weighting of the a type, the weight weighting of the B type, the weight weighting of the C type, and the weight weighting of the D type.
And S303, determining a target fault type from the candidate fault types according to the weight weighting number corresponding to the candidate fault types.
Optionally, in this embodiment, the candidate fault type whose weight corresponding to the candidate fault type is greater than the preset second threshold may be determined as the target fault type. Optionally, a value of the second threshold may be determined according to a weight value corresponding to each fault type and a historical outbound failure frequency corresponding to each fault type, and exemplarily, if a weight value corresponding to a certain fault type is 0.1 and a historical outbound failure frequency corresponding to the certain fault type is 5, the second threshold may be 0.5. Optionally, in this embodiment, the weighted numbers corresponding to the candidate fault types may be further arranged in an order from large to small, and the candidate fault types arranged in the first 3 are taken as the target fault types, or the candidate fault types arranged in the first 2 may be taken as the target fault types.
In the embodiment, the candidate fault type of the outbound failure occurring in the time period to be predicted can be screened out from the multiple fault types according to the outbound frequency corresponding to each fault type, so that the weight weighting corresponding to the candidate fault type can be quickly determined according to the weight weighting of each fault type.
In the scenario that the candidate fault type of the outbound failure occurring within the time period to be predicted is determined according to the number of outbound failure times corresponding to each fault type, in an embodiment, the step S301 includes:
and determining the outbound failure times larger than the preset time threshold value corresponding to the fault type as candidate fault types.
Specifically, in this embodiment, the number of outbound failure times corresponding to each fault type may be compared with a preset number threshold, and the fault type corresponding to the number of outbound failure times greater than the preset number threshold is determined as the candidate fault type. Optionally, the determined candidate fault type may be one fault type, or may be multiple fault types. Illustratively, taking a preset number threshold as 5 times as an example, if the number of outbound failures corresponding to the fault type a is 8 times, the number of outbound failures corresponding to the fault type B is 15 times, and the number of outbound failures corresponding to the fault type C is 2 times, the fault type a and the fault type B may be determined as the candidate fault types.
In this embodiment, by comparing the outbound failure times corresponding to each fault type with the preset time threshold, the fault type corresponding to the outbound failure times greater than the preset time threshold can be quickly determined, so that the fault type corresponding to the outbound failure times greater than the time threshold can be determined as the candidate fault type, that is, the efficiency of determining the candidate fault type is improved by the method.
In some scenes, when the outbound failure rate is monitored to be high, alarm prompt information can be output to prompt a user that the outbound failure rate in a time period to be predicted is high. In one embodiment, the method further comprises: and outputting alarm prompt information under the condition that the outbound failure rate is greater than a preset first threshold value.
Specifically, in this embodiment, when the outbound failure rate of the outbound system is greater than the preset first threshold, the alarm prompt information may be output. Optionally, the alarm prompt message may be a message that an alarm lamp flashes, or may also be a voice prompt message, or may be a text prompt message. Illustratively, the preset first threshold may be 50%, and if the obtained outbound failure rate is greater than 50%, an alarm prompt message may be output. Further, if the outbound failure rate is an outbound failure rate in a time period of 8-00-9 a day, the output alarm prompt message may be a text prompt message of "8.
In the embodiment, when the outbound failure rate is greater than the preset first threshold, the user can be informed in time by outputting the alarm prompt message, so that the user can check the outbound system in time, the fault of the outbound system is solved as early as possible, and the normal use of the outbound system is ensured.
In the above scenario where the time period to be predicted is input into a preset neural network model, the neural network model is a pre-trained neural network model. In one embodiment, as shown in fig. 4, the training process of the neural network model includes:
s401, acquiring the total outbound failure times in a sample time period and standard outbound failure times corresponding to multiple failure types caused by the failures of an outbound system.
Optionally, in this embodiment, the outbound system in the sample time period may be monitored, and the total number of outbound failure times of the outbound system in the sample time period and the standard number of outbound failure times corresponding to multiple failure types caused by the failure of the outbound system may be obtained. Illustratively, between a sample time period 08. The outbound system is monitored and the results obtained may be as shown in table 2.
TABLE 2
S402, determining the standard outbound failure rate corresponding to the sample time period according to the standard outbound failure times and the total outbound failure times.
Optionally, in this embodiment, a sum of standard outbound failure times corresponding to various fault types may be taken, and a ratio of the sum to the total outbound failure times is determined as the standard outbound failure rate corresponding to the sample time period. Further, as an optional implementation manner, the ratio of the sum to the total number of outbound failure times may be rounded, and the rounded ratio is determined as the standard outbound failure rate corresponding to the sample time period. For example, the sample time period is 08.
And S403, inputting the sample time period into the initial neural network model, and predicting the sample outbound failure rate in the sample time period and the sample outbound failure times corresponding to multiple fault types occurring in the sample time period.
Specifically, before predicting the sample outbound failure rate in the sample time period and the sample outbound failure times corresponding to the multiple failure types occurring in the sample time period, data normalization needs to be performed on the standard outbound failure times. Optionally, the data may be pre-processed using a Z-score normalization method, and scaled to fall within a specific range, for example, for a standard series of outbound failure times x 1 ,x 2 ,...,x n The changes made may be:
here, the
Wherein s is the standard deviation of the original data,
is the mean of the raw data. Then the new sequence y 1 ,y 2 ,...,y n Has a mean value of 0 and a variance of 1, and is dimensionless.
Optionally, after the data normalization is performed on the standard outbound failure times, the normalized standard outbound failure times may also be set as data types that can be identified by the LSTM, and then the processed sample time period is used as the input of the neural network, and the output of the neural network is the outbound failure rate in the sample time period and the outbound failure times corresponding to multiple fault types caused by the faults of the outbound system in the sample time period.
In addition, before the initial neural network model is trained, the acquired sample set may be divided into a training set and a test set according to a preset ratio, for example, the ratio may be 7: a scale of 3 divides the sample set into a training set and a test set.
S404, training the initial neural network model according to the standard outbound failure rate, the standard outbound failure times, the sample outbound failure rate and the sample outbound failure times to obtain the neural network model.
It can be understood that training the initial neural network model requires building a loss function and an optimizer of the neural network, where the loss function is selected as a cross entropy loss function and the optimizer is selected as an adaptive gradient descent algorithm.
In the process of ending the training of the neural network, observing the fitting condition of the neural network, firstly observing the change condition of the loss function during the training, and indicating that the model is not very stable under the condition of loss oscillation, and possibly having the problems of input data selection or unreasonable loss function design and the like. The accuracy of the outbound failure rate in the time period output by the neural network and the accuracy of the outbound failure times corresponding to various fault types caused by the faults of the outbound system in the time period in the training set and the verification set are verified in the training process, if the accuracy of the training set is found to be high, the accuracy of the verification set is not high enough, and the situation that the model is over-fitted is shown, the problem that the prediction result is poor is caused, and the model needs to be optimized. Optionally, in this embodiment, a value of a first loss function of the initial neural network model may be obtained according to the standard outbound failure rate and the sample outbound failure rate output by the initial neural network model, a value of a second loss function of the initial neural network model is obtained according to the standard outbound failure times corresponding to each fault type and the sample outbound failure times of each fault type output by the initial neural network model, parameters of the initial neural network model are adjusted by using the value of the first loss function and the value of the second loss function until the values of the first loss function and the second loss function reach a stable value or a minimum value, and the initial neural network model at this time is determined as the neural network model. For example, as shown in fig. 5, in this embodiment, relevant monitoring data of the outbound system may be collected first, the monitoring data is processed, then the processed monitoring data is used to train the LSTM monitoring model, and then the trained monitoring model is used to predict the outbound failure rate of the time period to be predicted and the outbound failure times corresponding to multiple fault types caused by the faults of the outbound system in the time period to be predicted.
In the embodiment, by acquiring the total outbound failure times in the sample time period and the standard outbound failure times corresponding to multiple fault types caused by the faults of the outbound system, the standard outbound times and the total outbound failure times can be quickly determined, so that the standard outbound failure rate corresponding to the sample time period can be quickly determined, the sample time period can be input into the initial neural network model, and the sample outbound failure rate in the sample time period and the sample outbound failure times corresponding to the multiple fault types occurring in the sample time period can be predicted; furthermore, the initial neural network model can be accurately trained according to the standard outbound failure rate, the standard outbound failure times, the sample outbound failure rate and the sample outbound failure times, and the accuracy of the obtained neural network model is improved.
In a specific embodiment, a method for analyzing an outbound fault provided by the present application is described as a complete embodiment, and the method includes the following steps:
s1, acquiring the total outbound failure times in a sample time period and standard outbound failure times corresponding to multiple fault types caused by faults of an outbound system;
s2, determining a standard outbound failure rate corresponding to the sample time period according to each standard outbound frequency and the total outbound failure frequency;
s3, inputting the sample time period into the initial neural network model, and predicting the sample outbound failure rate in the sample time period and the sample outbound failure times corresponding to multiple fault types occurring in the sample time period;
s4, training the initial neural network model according to the standard outbound failure rate, the standard outbound failure times, the sample outbound failure rate and the sample outbound failure times to obtain a neural network model;
s5, inputting a time period to be predicted into a preset neural network model, and predicting the outbound failure rate in the time period and the outbound failure times corresponding to multiple fault types caused by the faults of the outbound system in the time period;
and S6, outputting alarm prompt information under the condition that the outbound failure rate is greater than a preset first threshold value.
S7, under the condition that the outbound failure rate is greater than a preset first threshold value, obtaining a weight weighting number corresponding to each fault type according to each outbound failure frequency and a preset weight value corresponding to each fault type;
s8, determining candidate fault types of the outbound failures occurring in the time period according to the outbound failure times, and determining the outbound failure times larger than a preset time threshold value to correspond to the fault types as the candidate fault types;
s9, determining the weight weighting number corresponding to the candidate fault type according to the weight weighting number;
and S10, determining a target fault type from the candidate fault types according to the weight weighting number corresponding to the candidate fault types, and determining the candidate fault type with the weight weighting number larger than a preset second threshold value as the target fault type.
For the working principle of the outbound fault analysis method provided in this embodiment, please refer to the detailed description in the above embodiments, which is not repeated herein.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the application also provides an outbound fault analysis device for realizing the outbound fault analysis method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method, so that specific limitations in one or more embodiments of the outbound fault analysis device provided below can be referred to the limitations of the outbound fault analysis method in the above, and details are not described here.
In one embodiment, as shown in fig. 6, there is provided an outbound fault analysis apparatus including: a first prediction module 11, a calculation module 12 and a first determination module 13, wherein:
the first prediction module 11 is configured to input a time period to be predicted into a preset neural network model, and predict an outbound failure rate in the time period and outbound failure times corresponding to multiple failure types caused by a failure of an outbound system in the time period.
And the calculating module 12 is configured to, when the outbound failure rate is greater than the preset first threshold, obtain a weight weighting number corresponding to each fault type according to each outbound failure frequency and a preset weight value corresponding to each fault type.
And the first determining module 13 is configured to determine a target fault type of the outbound failure occurring within the time period according to the number of times of the outbound failures and the weight number of each weight.
The outbound fault analysis apparatus provided in this embodiment may perform the method embodiments, and the implementation principle and technical effects are similar, which are not described herein again.
In one embodiment, as shown in fig. 7, the first determining module 13 includes: a first determining unit 131, a second determining unit 132, and a third determining unit 133, wherein:
the first determining unit 131 is configured to determine candidate fault types of outbound failures occurring within a time period according to the number of outbound failures.
And a second determining unit 132, configured to determine, according to each weighted value, a weighted value corresponding to the candidate fault type.
The third determining unit 133 is configured to determine the target fault type from the candidate fault types according to the weighting number corresponding to the candidate fault types.
The outbound fault analysis apparatus provided in this embodiment may implement the method embodiments described above, and its implementation principle and technical effect are similar, which are not described herein again.
In an embodiment, the third determining unit 133 is configured to determine, as the target fault type, the candidate fault type with the weighting number greater than the preset second threshold.
The outbound fault analysis apparatus provided in this embodiment may implement the method embodiments described above, and its implementation principle and technical effect are similar, which are not described herein again.
In an embodiment, the second determining unit 131 is configured to determine the number of outbound failures greater than a preset number threshold as a candidate fault type corresponding to the fault type.
The outbound fault analysis apparatus provided in this embodiment may implement the method embodiments described above, and its implementation principle and technical effect are similar, which are not described herein again.
In one embodiment, as shown in fig. 8, the apparatus further comprises: an alarm module 14, wherein:
and the alarm module 14 is configured to output alarm prompt information when the outbound failure rate is greater than a preset first threshold.
The outbound fault analysis apparatus provided in this embodiment may implement the method embodiments described above, and its implementation principle and technical effect are similar, which are not described herein again.
In one embodiment, as shown in fig. 9, the apparatus further comprises: an acquisition module 15, a second determination module 16, a second prediction module 17, and a training module 18, wherein:
and the obtaining module 15 is configured to obtain the total number of outbound failures in the sample time period and the standard number of outbound failures corresponding to multiple failure types caused by the failure of the outbound system.
And the second determining module 16 is configured to determine a standard outbound failure rate corresponding to the sample time period according to each standard outbound frequency and the total outbound failure frequency.
And the second prediction module 17 is configured to input the sample time period into the initial neural network model, and predict a sample outbound failure rate in the sample time period and sample outbound failure times corresponding to multiple fault types occurring in the sample time period.
And the training module 18 is used for training the initial neural network model according to the standard outbound failure rate, the times of various standard outbound failures, the sample outbound failure rate and the times of various sample outbound failures to obtain the neural network model.
The outbound fault analysis apparatus provided in this embodiment may implement the method embodiments described above, and its implementation principle and technical effect are similar, which are not described herein again.
All or part of each module in the outbound fault analysis device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 10. The computer device comprises a processor, a memory, a communication interface, a display screen and an input device which are connected through a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The communication interface of the computer device is used for communicating with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a method of outbound fault analysis. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on a shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the configuration shown in fig. 10 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
inputting a time period to be predicted into a preset neural network model, and predicting the outbound failure rate in the time period and the outbound failure times corresponding to multiple fault types caused by the faults of an outbound system in the time period;
under the condition that the outbound failure rate is greater than a preset first threshold, obtaining a weight weighting number corresponding to each fault type according to each outbound failure frequency and a preset weight value corresponding to each fault type;
and determining the target fault type of the outbound failure occurring in the time period according to the outbound failure times and the weighted number of the weights.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
determining candidate fault types of the outbound failures occurring in the time period according to the number of the outbound failures;
determining the weight weighting number corresponding to the candidate fault type according to the weight weighting number;
and determining a target fault type from the candidate fault types according to the weight weighting number corresponding to the candidate fault types.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and determining the candidate fault type with the weight number greater than a preset second threshold value as a target fault type.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and determining the corresponding fault type of the outbound failure times larger than the preset time threshold value as a candidate fault type.
In one embodiment, the processor when executing the computer program further performs the steps of:
and outputting alarm prompt information under the condition that the outbound failure rate is greater than a preset first threshold value.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring the total outbound failure times in a sample time period and standard outbound failure times corresponding to multiple failure types caused by the failures of an outbound system;
determining a standard outbound failure rate corresponding to the sample time period according to each standard outbound frequency and the total outbound failure frequency;
inputting the sample time period into an initial neural network model, and predicting the sample outbound failure rate in the sample time period and the sample outbound failure times corresponding to multiple fault types occurring in the sample time period;
and training the initial neural network model according to the standard outbound failure rate, the standard outbound failure times, the sample outbound failure rate and the sample outbound failure times to obtain the neural network model.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
inputting a time period to be predicted into a preset neural network model, and predicting the outbound failure rate in the time period and the outbound failure times corresponding to multiple failure types caused by the self failure of an outbound system in the time period;
under the condition that the outbound failure rate is greater than a preset first threshold, obtaining a weight weighting number corresponding to each fault type according to each outbound failure frequency and a preset weight value corresponding to each fault type;
and determining the target fault type of the outbound failure occurring in the time period according to the outbound failure times and the weighted number of the weights.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining candidate fault types of the outbound failure occurring in a time period according to the number of the outbound failure;
determining the weight weighting number corresponding to the candidate fault type according to the weight weighting number;
and determining the target fault type from the candidate fault types according to the weight number corresponding to the candidate fault types.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and determining the candidate fault type with the weight number greater than a preset second threshold value as a target fault type.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and determining the outbound failure times larger than the preset time threshold value corresponding to the fault type as candidate fault types.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and outputting alarm prompt information under the condition that the outbound failure rate is greater than a preset first threshold value.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring the total outbound failure times in a sample time period and standard outbound failure times corresponding to multiple fault types caused by the faults of an outbound system;
determining a standard outbound failure rate corresponding to the sample time period according to each standard outbound frequency and the total outbound failure frequency;
inputting the sample time period into an initial neural network model, and predicting the sample outbound failure rate in the sample time period and the sample outbound failure times corresponding to multiple fault types occurring in the sample time period;
and training the initial neural network model according to the standard outbound failure rate, the standard outbound failure times, the sample outbound failure rate and the sample outbound failure times to obtain the neural network model.
In one embodiment, a computer program product is provided, comprising a computer program which when executed by a processor performs the steps of:
inputting a time period to be predicted into a preset neural network model, and predicting the outbound failure rate in the time period and the outbound failure times corresponding to multiple fault types caused by the faults of an outbound system in the time period;
under the condition that the outbound failure rate is greater than a preset first threshold, obtaining a weight weighting number corresponding to each fault type according to each outbound failure frequency and a preset weight value corresponding to each fault type;
and determining the target fault type of the outbound failure in the time period according to the number of times of the outbound failure and the weighted number of the weights.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining candidate fault types of the outbound failures occurring in the time period according to the number of the outbound failures;
determining the weight weighting number corresponding to the candidate fault type according to the weight weighting number;
and determining the target fault type from the candidate fault types according to the weight number corresponding to the candidate fault types.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and determining the candidate fault type with the weight number greater than a preset second threshold value as a target fault type.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and determining the outbound failure times larger than the preset time threshold value corresponding to the fault type as candidate fault types.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and outputting alarm prompt information under the condition that the outbound failure rate is greater than a preset first threshold value.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring the total outbound failure times in a sample time period and standard outbound failure times corresponding to multiple fault types caused by the faults of an outbound system;
determining a standard outbound failure rate corresponding to the sample time period according to each standard outbound frequency and the total outbound failure frequency;
inputting the sample time period into an initial neural network model, and predicting the sample outbound failure rate in the sample time period and the sample outbound failure times corresponding to multiple fault types occurring in the sample time period;
and training the initial neural network model according to the standard outbound failure rate, the standard outbound failure times, the sample outbound failure rate and the sample outbound failure times to obtain the neural network model.
It should be noted that, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, databases, or other media used in the embodiments provided herein may include a variety of non-volatile and volatile memories, among others. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), magnetic Random Access Memory (MRAM), ferroelectric Random Access Memory (FRAM), phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in the embodiments provided herein may include a variety of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. An outbound fault analysis method, the method comprising:
inputting a time period to be predicted into a preset neural network model, and predicting the outbound failure rate in the time period and the outbound failure times corresponding to multiple failure types caused by the self failure of an outbound system in the time period;
under the condition that the outbound failure rate is greater than a preset first threshold, obtaining a weight weighting number corresponding to each fault type according to each outbound failure frequency and a preset weight value corresponding to each fault type;
and determining the target fault type of the outbound failure occurring in the time period according to the number of the outbound failures and the weight of the weights.
2. The method of claim 1, wherein determining the target failure type of the outbound failure occurring within the time period according to the number of times of each outbound failure and each weighted number of weights comprises:
determining candidate fault types of the outbound failures occurring in the time period according to the number of the outbound failures;
determining the weight weighting number corresponding to the candidate fault type according to the weight weighting numbers;
and determining the target fault type from the candidate fault types according to the weight and the weight corresponding to the candidate fault types.
3. The method according to claim 2, wherein the determining the target fault type from the candidate fault types according to the weighting number corresponding to the candidate fault types comprises:
and determining the candidate fault type with the weight number greater than a preset second threshold value as the target fault type.
4. The method of claim 2, wherein determining the candidate failure types of outbound failures occurring within the time period according to the number of each outbound failure comprises:
and determining the corresponding fault type of the outbound failure times larger than the preset time threshold value as the candidate fault type.
5. The method according to any one of claims 1-4, further comprising:
and outputting alarm prompt information under the condition that the outbound failure rate is greater than the preset first threshold value.
6. The method of claim 1, wherein the training process of the neural network model comprises:
acquiring the total outbound failure times in a sample time period and standard outbound failure times corresponding to multiple fault types caused by the faults of an outbound system;
determining a standard outbound failure rate corresponding to the sample time period according to the standard outbound failure times and the total outbound failure times;
inputting the sample time period into an initial neural network model, and predicting the sample outbound failure rate in the sample time period and the sample outbound failure times corresponding to multiple fault types occurring in the sample time period;
and training the initial neural network model according to the standard outbound failure rate, the standard outbound failure times, the sample outbound failure rate and the sample outbound failure times to obtain the neural network model.
7. An outbound fault analysis apparatus, the apparatus comprising:
the prediction module is used for inputting a time period to be predicted into a preset neural network model, and predicting the outbound failure rate in the time period and the outbound failure times corresponding to multiple fault types caused by the faults of the outbound system in the time period;
the calculation module is used for obtaining the weight weighting number corresponding to each fault type according to the number of outbound failure times and the preset weight value corresponding to each fault type under the condition that the outbound failure rate is greater than a preset first threshold value;
and the determining module is used for determining the target fault type of the outbound failure occurring in the time period according to the number of times of the outbound failure and the weighted number of the weights.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 1 to 6 when executing the computer program.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 6 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211182229.2A CN115665323A (en) | 2022-09-27 | 2022-09-27 | Outbound fault analysis method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211182229.2A CN115665323A (en) | 2022-09-27 | 2022-09-27 | Outbound fault analysis method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115665323A true CN115665323A (en) | 2023-01-31 |
Family
ID=84986321
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211182229.2A Pending CN115665323A (en) | 2022-09-27 | 2022-09-27 | Outbound fault analysis method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115665323A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110349289A (en) * | 2019-06-21 | 2019-10-18 | 东软集团股份有限公司 | Failure prediction method, device, storage medium and electronic equipment |
| CN110796487A (en) * | 2019-10-18 | 2020-02-14 | 上海钧正网络科技有限公司 | Quantity prediction method, device, computer equipment and storage medium |
| CN111435482A (en) * | 2019-01-14 | 2020-07-21 | 顺丰科技有限公司 | Outbound model construction method, outbound method, device and storage medium |
| CN112631888A (en) * | 2020-12-30 | 2021-04-09 | 航天信息股份有限公司 | Fault prediction method and device of distributed system, storage medium and electronic equipment |
-
2022
- 2022-09-27 CN CN202211182229.2A patent/CN115665323A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111435482A (en) * | 2019-01-14 | 2020-07-21 | 顺丰科技有限公司 | Outbound model construction method, outbound method, device and storage medium |
| CN110349289A (en) * | 2019-06-21 | 2019-10-18 | 东软集团股份有限公司 | Failure prediction method, device, storage medium and electronic equipment |
| CN110796487A (en) * | 2019-10-18 | 2020-02-14 | 上海钧正网络科技有限公司 | Quantity prediction method, device, computer equipment and storage medium |
| CN112631888A (en) * | 2020-12-30 | 2021-04-09 | 航天信息股份有限公司 | Fault prediction method and device of distributed system, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2018523885A (en) | Classifying user behavior as abnormal | |
| CN113448787A (en) | Wafer abnormity analysis method and device, electronic equipment and readable storage medium | |
| CN113887845B (en) | Extreme event prediction method, device, equipment and storage medium | |
| CN113946986A (en) | Method and device for evaluating average time before product failure based on accelerated degradation test | |
| CN115641019A (en) | Index anomaly analysis method and device, computer equipment and storage medium | |
| CN117235664A (en) | Fault diagnosis method and system for power distribution communication equipment and computer equipment | |
| CN114626747A (en) | Weight analysis method, device, equipment and medium for resource acquisition influence factors | |
| CN113946983A (en) | Method and device for evaluating weak links of product reliability and computer equipment | |
| CN115665323A (en) | Outbound fault analysis method and device, computer equipment and storage medium | |
| CN115759742A (en) | Enterprise risk assessment method and device, computer equipment and storage medium | |
| CN115169155A (en) | Engine fault prediction method and device, computer equipment and storage medium | |
| CN115619261A (en) | Job label portrait data processing method and device and computer equipment | |
| CN115630527B (en) | Exception model detection method, device, computer equipment and storage medium | |
| CN116681203A (en) | Enterprise management consultation method and system based on big data analysis | |
| CN115587805B (en) | Laboratory environment test project determining method and device and environment comprehensive test evaluation method and device | |
| US20230359449A1 (en) | Learning-augmented application deployment pipeline | |
| CN117056307A (en) | Database management method, apparatus, device, storage medium, and program product | |
| CN115098331A (en) | IO (input/output) blocking detection method and device, computer equipment, storage medium and product | |
| CN116577586A (en) | Power equipment fault monitoring method, device, computer equipment and storage medium | |
| CN117575772A (en) | Abnormal user detection method and device, computer equipment and storage medium | |
| CN117407153A (en) | Interface access control method, device, computer equipment, storage medium and product | |
| CN117495131A (en) | Power consumption data prediction method, device, computer equipment and storage medium | |
| CN116611507A (en) | Abnormal transaction identification model construction method, abnormal transaction identification method and device | |
| CN114860560A (en) | Server abnormality identification method, apparatus, device, storage medium, and program product | |
| CN118297376A (en) | Risk prediction method, apparatus, device, storage medium, and program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |